Hacker Papers
- 376
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Hacker News threads
- 377
Lessons from Building Acoustic Models with a Million Hours of Speech
Hacker News threads
- 378
BERT Rediscovers the Classical NLP Pipeline
Hacker News threads
- 379
Deep Learning Recommendation Model for Personalization and Recommendation Systems
Hacker News threads
- 380
Hamiltonian Neural Networks
Hacker News threads
- 381
A strong no-go theorem on the Wigner's friend paradox
Hacker News threads
- 382
Comparing the Effects of DNS, DoT, and DoH on Web Performance
Hacker News threads
- 383
Attention is not not Explanation
Hacker News threads
- 384
KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning
Hacker News threads
- 385
Failure of Normalization in Impredicative Type Theory with Proof-Irrelevant Propositional Equality
Hacker News threads
- 386
Array Languages Make Neural Networks Fast
Hacker News threads
- 387
OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network
Hacker News threads
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.











